This paper proposes a remote sensing image classification approach that utilizes the ResNet and EfficientNet models. Remote sensing images play a crucial role in various applications, such as land cover mapping and environmental monitoring. The ResNet and EfficientNet models are deep convolution neural networks known for their effectiveness in image classification tasks. In this study, we investigate their performance in the context of remote sensing image classification. We conduct experiments on a benchmark dataset and compare the results with other state-of-the-art methods. Our findings demonstrate the efficacy of the ResNet and EfficientNet models for remote sensing image classification, with both models achieving high accuracy and outperforming existing approaches. The proposed approach shows promise in enhancing the accuracy and efficiency of remote sensing image analysis, paving the way for improved land cover mapping and environmental monitoring applications.